microsoft-graph-api

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Recommends the global installation of the official @membranehq/cli utility from the npm registry to facilitate communication with the platform.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute specific CLI commands such as membrane login, membrane connect, and membrane action run for managing Microsoft Graph API connections and performing data operations.
  • [PROMPT_INJECTION]: Identified an indirect prompt injection surface as the skill retrieves and processes data from external Microsoft 365 services (emails, drives, contacts) which may contain user-generated content.
  • Ingestion points: Data returned from Microsoft Graph API calls processed in SKILL.md.
  • Boundary markers: None specified in the instructions.
  • Capability inventory: The skill utilizes membrane action run and membrane request for executing API actions and proxying network requests.
  • Sanitization: No explicit validation or filtering of incoming API data is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 05:10 PM